© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 198910
    Prev
    Next
    INDEX
    Explanations

    rice water rinse, wild rice, paddy fields

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_12_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ượu
    0.41
    Thai
    0.40
     tattha
    0.39
    🍳
    0.38
    ską
    0.38
     பயன
    0.37
    OffsetX
    0.37
    Sunglasses
    0.36
     ناخذ
    0.36
    ༼
    0.36
    POSITIVE LOGITS
    '
    0.44
     legitim
    0.43
     hypothes
    0.39
     exoner
    0.37
    詆
    0.37
    uldig
    0.36
    meter
    0.35
    ЕН
    0.35
    らし
    0.35
     Buckley
    0.35
    Activations Density 0.000%

    No Known Activations